gpt-4.5-preview
OpenAIlegacy model Its test configurations are retired, so it is no longer run. The figures are from its best legacy runs, scored as they ran at the time; it is not ranked.
- average
- 33.5
- benchmarksof 12
- 3
- seconds per inputmean response time
- 50.9
By benchmark
| Benchmark | ScoreThe best legacy run on each benchmark, on the benchmark's metric scaled to 0–100. ± is the 95% sampling margin, from resampling the run's inputs. | RankRank among all current models on that benchmark; ≈ for models that cannot be told apart within sampling error. Legacy models are not ranked. | Per 1,000 docs | s / input | Best run |
|---|---|---|---|---|---|
| Bibliographic Dataolder run | 25.1 | – | –– run | 96.03 | T0026 · 8 Apr 2025prompt.txt |
| Business Lettersolder run | 59.0 | – | –– run | 11.97 | T0011 · 5 Mar 2025prompt.txt |
| Fraktur Advertsolder run | 16.3 | – | –– run | 44.8 | T0081 · 9 May 2025prompt_optimized.txt |
Not run on: Blacklist Cards, Book Advert XML Repair, Company Lists, Duty Rosters, General Meeting Minutes, Library Cards, Magazine Pages, Medieval Manuscripts, Personnel Cards.
Every run
- T0081Fraktur Adverts9 May 2025 · legacy configuration16.3–
- T0081Fraktur Adverts7 May 2025 · legacy configuration1.0–
- T0041Business Letters11 Apr 2025 · 32 signed letters · legacy configuration63.0–
- T0040Business Letters11 Apr 2025 · 25 unsigned letters · legacy configuration46.0–
- T0011Business Letters11 Apr 2025 · all 57 letters · legacy configuration58.0–
- T0026Bibliographic Data8 Apr 2025 · legacy configuration25.1–
- T0011Business Letters1 Apr 2025 · all 57 letters · legacy configuration57.0–
- T0011Business Letters5 Mar 2025 · all 57 letters · legacy configuration59.0–